Skip navigation

Zastosuj identyfikator do podlinkowania lub zacytowania tej pozycji: http://hdl.handle.net/20.500.12128/147
Tytuł: Fully Connected Neural Networks Ensemble with Signal Strength Clustering for Indoor Localization in Wireless Sensor Networks
Autor: Bernaś, Marcin
Płaczek, Bartłomiej
Słowa kluczowe: Neural networks; Indoor positioning systems; Mobile computing; Sensor nodes
Data wydania: 2015
Źródło: International Journal of Distributed Sensor Networks, (2015), art. ID 403242, s. 1-10
Abstrakt: The paper introduces a method which improves localization accuracy of the signal strength fingerprinting approach. According to the proposed method, entire localization area is divided into regions by clustering the fingerprint database. For each region a prototype of the received signal strength is determined and a dedicated artificial neural network (ANN) is trained by using only those fingerprints that belong to this region (cluster). Final estimation of the location is obtained by fusion of the coordinates delivered by selected ANNs. Sensor nodes have to store only the signal strength prototypes and synaptic weights of the ANNs in order to estimate their locations. This approach significantly reduces the amount of memory required to store a received signal strength map. Various ANN topologies were considered in this study. Improvement of the localization accuracy as well as speed-up of learning process was achieved by employing fully connected neural networks. The proposed method was verified and compared against state-of-the-art localization approaches in realworld indoor environment by using both stationary andmobile sensor nodes.
URI: http://hdl.handle.net/20.500.12128/147
ISSN: 1550-1329
1550-1477
Pojawia się w kolekcji:Artykuły (WINOM)

Pliki tej pozycji:
Plik Opis RozmiarFormat 
Bernas_Fully Connected Neural Networks Ensemble with Signal Strength Clustering for Indoor Localization in Wireless Sensor Networks.pdf16,95 MBAdobe PDFPrzejrzyj / Otwórz
Pokaż pełny rekord


Uznanie Autorstwa 3.0 Polska Creative Commons Creative Commons